{"id":"https://openalex.org/W4411119737","doi":"https://doi.org/10.18653/v1/2025.mwe-1.4","title":"Using LLMs to Advance Idiom Corpus Construction","display_name":"Using LLMs to Advance Idiom Corpus Construction","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411119737","doi":"https://doi.org/10.18653/v1/2025.mwe-1.4"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.mwe-1.4","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.mwe-1.4","pdf_url":"https://aclanthology.org/2025.mwe-1.4.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st Workshop on Multiword Expressions (MWE 2025)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.mwe-1.4.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042425959","display_name":"Do\u011fukan Arslan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Do\u011fukan Arslan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072839884","display_name":"H\u00fcseyin \u00c7akmak","orcid":"https://orcid.org/0000-0002-1463-7606"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H\u00fcseyin An\u0131l \u00c7akmak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030279774","display_name":"G\u00fcl\u015fen Eryi\u011fit","orcid":"https://orcid.org/0000-0003-4607-7305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gulsen Eryigit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026817367","display_name":"Joakim Nivre","orcid":"https://orcid.org/0000-0002-7873-3971"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joakim Nivre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05523289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12881","display_name":"linguistics and terminology studies","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10759","display_name":"Translation Studies and Practices","score":0.9629999995231628,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6135843992233276},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4314206838607788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32729655504226685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6135843992233276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4314206838607788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32729655504226685}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.mwe-1.4","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.mwe-1.4","pdf_url":"https://aclanthology.org/2025.mwe-1.4.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st Workshop on Multiword Expressions (MWE 2025)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.mwe-1.4","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.mwe-1.4","pdf_url":"https://aclanthology.org/2025.mwe-1.4.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st Workshop on Multiword Expressions (MWE 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411119737.pdf","grobid_xml":"https://content.openalex.org/works/W4411119737.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Idiom":[0],"corpora":[1,16,39],"typically":[2],"include":[3],"both":[4],"idiomatic":[5,11],"and":[6,22,56,96],"literal":[7],"examples":[8],"of":[9,30,49,94,124],"potentially":[10],"expressions,":[12],"but":[13],"creating":[14],"such":[15],"traditionally":[17],"requires":[18],"substantial":[19],"expert":[20],"effort":[21],"cost.In":[23],"this":[24],"article,":[25],"we":[26],"explore":[27],"the":[28,47,107,112,134,141],"use":[29],"large":[31],"language":[32],"models":[33,55,73,101,143],"(LLMs)":[34],"to":[35,139],"generate":[36],"synthetic":[37,50,64,76,86,104,131,146],"idiom":[38],"as":[40],"a":[41,117],"more":[42],"time-and":[43],"cost-efficient":[44],"alternative.We":[45],"evaluate":[46],"effectiveness":[48],"data":[51,65,77,87,105,113,132,147],"in":[52,59,92,116],"training":[53],"task-specific":[54,98,142],"testing":[57],"GPT-4":[58],"few-shot":[60,149],"prompting":[61,150],"setting":[62],"using":[63],"for":[66],"idiomaticity":[67,99],"detection.Our":[68],"findings":[69],"reveal":[70],"that":[71,110],"although":[72],"trained":[74,82,102,144],"on":[75,83,103],"perform":[78],"worse":[79],"than":[80],"those":[81],"human-generated":[84],"data,":[85],"generation":[88],"offers":[89],"considerable":[90],"advantages":[91],"terms":[93],"cost":[95],"time.Specifically,":[97],"detection":[100],"outperform":[106],"general-purpose":[108],"LLM":[109],"generated":[111],"when":[114,148],"evaluated":[115],"zero-shot":[118],"setting,":[119],"achieving":[120],"an":[121],"average":[122],"improvement":[123],"11":[125],"percentage":[126],"points":[127],"across":[128],"four":[129],"languages.Moreover,":[130],"enhances":[133],"LLM's":[135],"performance,":[136],"enabling":[137],"it":[138],"match":[140],"with":[145],"is":[151],"applied.":[152]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}